OCR doesnt works (Cyrillic characters)

  • Last Post 27 April 2023
Alexey Osheyko posted this 25 April 2023

I am planning to implement the ScanShare software product.

I am processing a bilingual document.

Question: Why  Cyrillic characters does not correctly recognized in the output PDF document?

I want to know your opinion. Is this not possible?

This is a fundamental criterion for a customer agreement.

Attached Files

luca.scarpati posted this 27 April 2023

Hi Alexey,


welcome on board cool!

Depends where you're trying to get it and what you're getting it with...a lot depends on the quality of your input document for example if you use a PDF it will be rasterized so if your input document is already poor in quality after rasterization it still loses some extra (that's normal rasterization steps).

However we are two engine (Omnipage and ABBYY) available in our Software, for example here a section inside our help&manual:

Just for info for case like yours and for common reason ABBYY is TOP for the Cyrillic characters but it is extra inside the license.


However if you need some extra and specific support for your input document please contact the support team, for sure they will know what to suggest and so you may not share documents or part of it in a public forum.


Best regards,